C# Onnx GroundingDINO 开放世界目标检测

news2024/10/5 16:00:30

介绍

效果

模型信息

项目

代码

下载

介绍

地址：https://github.com/IDEA-Research/GroundingDINO

Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

效果

在运行程序时，要注意输入的提示词的格式，类别之间以" . "隔开，并且确保类别名称在词典文件 vocab.txt里是存在的，而且输入提示词里的类别名称是你想要检测的目标类别，否则可能会检测不到目标的。

模型信息

Model Properties
-------------------------
---------------------------------------------------------------

Inputs
-------------------------
name：img
tensor：Float[-1, 3, -1, -1]
name：input_ids
tensor：Int64[-1, -1]
name：attention_mask
tensor：Bool[-1, -1]
name：position_ids
tensor：Int64[-1, -1]
name：token_type_ids
tensor：Int64[-1, -1]
name：text_token_mask
tensor：Bool[-1, -1, -1]
---------------------------------------------------------------

Outputs
-------------------------
name：logits
tensor：Float[-1, -1, -1]
name：boxes
tensor：Float[-1, -1, 4]
---------------------------------------------------------------

项目

代码

Form1

using OpenCvSharp;
using System;
using System.Collections.Generic;
using System.Drawing;
using System.Text;
using System.Windows.Forms;

namespace Onnx_Demo
{
public partial class Form1 : Form
{
public Form1()
{
InitializeComponent();
}

GroundingDINO groundingDINO = new GroundingDINO("model/groundingdino_swint_ogc.onnx", 0.3f, "model/vocab.txt", 0.25f, true);

string image_path = "";
string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";

StringBuilder sb = new StringBuilder();

Mat image;
Mat result_image;

private void button2_Click(object sender, EventArgs e)
{
OpenFileDialog ofd = new OpenFileDialog();
ofd.Filter = fileFilter;
if (ofd.ShowDialog() != DialogResult.OK) return;

pictureBox1.Image = null;
pictureBox2.Image = null;
txtInfo.Text = "";

image_path = ofd.FileName;
pictureBox2.Image = new Bitmap(image_path);
image = new Mat(image_path);

}

private void button3_Click(object sender, EventArgs e)
{
if (image_path == "")
{
return;
}

if (String.IsNullOrEmpty(txt_input_text.Text))
{
return;
}

pictureBox1.Image = null;
txtInfo.Text = "检测中，请稍等……";
button3.Enabled = false;
if (pictureBox1.Image != null)
{
pictureBox1.Image.Dispose();
pictureBox1.Image = null;
}
Application.DoEvents();

String text_prompt = txt_input_text.Text;

List<Object> objects = groundingDINO.detect(image, text_prompt);

result_image = image.Clone();
sb.Clear();
for (int i = 0; i < objects.Count; i++)
{
Cv2.Rectangle(result_image, objects[i].box, new Scalar(0, 0, 255), 2);
Cv2.PutText(result_image, objects[i].text + " " + objects[i].prob.ToString("F2"), new OpenCvSharp.Point(objects[i].box.X, objects[i].box.Y), HersheyFonts.HersheySimplex, 1, new Scalar(0, 0, 255), 2); ;
sb.AppendLine(objects[i].text + " " + objects[i].prob.ToString("F2"));
}
pictureBox1.Image = new Bitmap(result_image.ToMemoryStream());

button3.Enabled = true;
txtInfo.Text = sb.ToString();

}

private void Form1_Load(object sender, EventArgs e)
{
image_path = "test_img/cat_dog.jpeg";
pictureBox2.Image = new Bitmap(image_path);
image = new Mat(image_path);
}
}
}

using OpenCvSharp;
using System;
using System.Collections.Generic;
using System.Drawing;
using System.Text;
using System.Windows.Forms;

namespace Onnx_Demo
{
    public partial class Form1 : Form
    {
        public Form1()
        {
            InitializeComponent();
        }

        GroundingDINO groundingDINO = new GroundingDINO("model/groundingdino_swint_ogc.onnx", 0.3f, "model/vocab.txt", 0.25f, true);

        string image_path = "";
        string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";

        StringBuilder sb = new StringBuilder();

        Mat image;
        Mat result_image;

        private void button2_Click(object sender, EventArgs e)
        {
            OpenFileDialog ofd = new OpenFileDialog();
            ofd.Filter = fileFilter;
            if (ofd.ShowDialog() != DialogResult.OK) return;

            pictureBox1.Image = null;
            pictureBox2.Image = null;
            txtInfo.Text = "";

            image_path = ofd.FileName;
            pictureBox2.Image = new Bitmap(image_path);
            image = new Mat(image_path);

        }

        private void button3_Click(object sender, EventArgs e)
        {
            if (image_path == "")
            {
                return;
            }

            if (String.IsNullOrEmpty(txt_input_text.Text))
            {
                return;
            }

            pictureBox1.Image = null;
            txtInfo.Text = "检测中，请稍等……";
            button3.Enabled = false;
            if (pictureBox1.Image != null)
            {
                pictureBox1.Image.Dispose();
                pictureBox1.Image = null;
            }
            Application.DoEvents();

            String text_prompt = txt_input_text.Text;

            List<Object> objects = groundingDINO.detect(image, text_prompt);

            result_image = image.Clone();
            sb.Clear();
            for (int i = 0; i < objects.Count; i++)
            {
                Cv2.Rectangle(result_image, objects[i].box, new Scalar(0, 0, 255), 2);
                Cv2.PutText(result_image, objects[i].text + " " + objects[i].prob.ToString("F2"), new OpenCvSharp.Point(objects[i].box.X, objects[i].box.Y), HersheyFonts.HersheySimplex, 1, new Scalar(0, 0, 255), 2); ;
                sb.AppendLine(objects[i].text + " " + objects[i].prob.ToString("F2"));
            }
            pictureBox1.Image = new Bitmap(result_image.ToMemoryStream());

            button3.Enabled = true;
            txtInfo.Text = sb.ToString();

        }

        private void Form1_Load(object sender, EventArgs e)
        {
            image_path = "test_img/cat_dog.jpeg";
            pictureBox2.Image = new Bitmap(image_path);
            image = new Mat(image_path);
        }
    }
}